Tag
Introduces Epi2Diff, a framework that maps LLM reasoning traces into cognitive episodes to predict human item difficulty, outperforming baselines and providing interpretable process evidence.
Introduces trajectory extrapolation error, a measure derived from transformer LM hidden states that predicts human reading times independently of and orthogonally to surprisal, revealing a dissociable component of incremental processing cost.
This paper proposes a structural and dynamical framework for modeling cognitive processes using iterative state transformations and semantic equivalence, integrating dynamical systems, category theory, and feedback mechanisms to model cognition as a process evolving toward stable interpretations.
This paper presents an in silico simulation of the RAMPHO episodic buffer using phonetic entropy from wav2vec 2.0 to dissociate informational and energetic masking in multi-talker environments, revealing a cognitive-acoustic Pareto optimization problem.
HumanLLM presents a framework for benchmarking and improving LLM anthropomorphism by modeling psychological patterns as interacting causal forces, constructing 244 patterns from academic literature and 11,359 multi-pattern scenarios. The approach demonstrates that authentic human alignment requires cognitive modeling rather than shallow behavioral mimicry, with HumanLLM-8B outperforming larger models like Qwen3-32B on multi-pattern dynamics.